Wasserstein Bounds for Euler and Randomized Midpoint Langevin Sampling with Noisy Gradients
math.ST, cs.NA, math.NA, stat.CO, stat.TH
Submitted: 2026-10-27
Updated: 2026-10-27
Comments: 26 pages, 3 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Stochastic-gradient Langevin methods are sampling algorithms that replace the gradient of the log probability density by a noisy, possibly biased evaluation.
Abstract
Stochastic-gradient Langevin methods are sampling algorithms that replace the gradient of the log probability density by a noisy, possibly biased evaluation. We study how such gradient-evaluation errors affect the Euler and randomized midpoint discretizations of Langevin dynamics by comparing each noisy chain with its exact-gradient counterpart. For continuously differentiable, strongly log-concave targets with globally Lipschitz gradients, we derive comparison bounds under a sub-Gaussian condition on the gradient noise. The resulting 2-Wasserstein bounds hold uniformly over iterations, and are linear in both the step size and the L squared norm of the evaluation bias, with a square-root dependence on dimensionality. To the best of our knowledge, no comparable 2-Wasserstein bounds have previously been established for randomized midpoint with noisy gradients. For Euler, our results complement recent Wasserstein bounds by allowing biased evaluations, and by not requiring additional regularity assumptions on the evaluation errors.
Related papers
- Sigmoid-FTRL: Design-Based Adaptive Neyman Allocation for AIPW Estimators
- Conformal Prediction for Dyadic Regression Under Complex Missingness
- Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel
- Bentkus-type asymptotic e-values
- Canonical Layer Inference for Deep Gaussian Processes via Symmetry-Breaking Augmentation
- High-Dimensional Asymptotics of Differentially Private PCA